My main goal is to develop the best AI-system for Dog's Activity Recognition. Our purpose is not just to have the best AI-system but to propose the best smart collar for dogs on the market !
In parallel I am developing the research and development part in order to explore other deep learning approaches. To success theses tasks I am working with a Machine Learning Engineer who is supporting me on the project related to the data.
In addition to the implementation of the machine learning project end-to-end, I am working on the setting up of tools to improve the project management, the data visualization and the workflow of our data. All of the tools implemented are open source.
I focused on the implementation of a recommender system (Products approach), Association Rules, scoring (of interest) and segmentations with the objective of developing the CRM.
I have implemented the time series forecasting with RNN with the aim of predicting the activity at the call center to scale the teams. I have also contributed to the implementation of a Proof Of Concept about the speech to text based on the algorithm WaveNet (DeepMind). I was able to use NLP’s algorithms in order to explore and to do an analysis of the surveys data.
About the tech I use: Pyspark, Hive, Dataiku,Tensorflow and Python
Consulting Data Scientist - Jagger & Lewis May 2018 - August 2018 - Set up Machine Learning & Deep Learning models to improve the quality of the solution
Mentor Data Scientist - Self Employed May 2018 - June 2018
Trainer at Quantmetry, Data Science Consulting December 2017 3 training days about the Machine Learning with Python and Big Data with Pyspark: - Algorithm of Machine Learning (Classification - Regression - Clustering) - Use cases (Risk Prediction) - Good practices (Exploratory Data Analysis) - Hadoop - Spark - Churn Prediction with Pyspark (MLlib)
Data Scientist at Pitchr March 2017 – November 2017 Implementation of an recommender system - Collaborative Filtering Approach - to sort smarter the people around the Pitchr's users. The goal was to sort a list of people caracterized by theirs professional skills in order to increase the number of connections between the users.
Talent sourcing specialist de la plateforme Pentalog, SkillValue s’appuie sur un pool de +400 000 Experts Tech & Marketing, dont +15 000 freelancers. Évaluations de compétences, missions, offres d’emploi : les consultants SkillValue vous aident à accélérer votre carrière.
Restez informé de l'actualité tech avec la newsletter Pentalog
À propos de Pentalog
Pentalog est une plateforme de services IT qui accompagne les entreprises dans leur production digitale et leur transformation en fournissant des ingénieurs et développeurs de classe mondiale. Ses 16 Delivery Centers et Agences dans le monde comptent plus de 1600 ingénieurs, développeurs, product designers et spécialistes marketing.